Picture for Gregory Plumb

Gregory Plumb

Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms

Jun 13, 2023
Figure 1 for Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Figure 2 for Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Figure 3 for Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Figure 4 for Where Does My Model Underperform? A Human Evaluation of Slice Discovery Algorithms
Viaarxiv icon

Evaluating Systemic Error Detection Methods using Synthetic Images

Add code
Jul 08, 2022
Figure 1 for Evaluating Systemic Error Detection Methods using Synthetic Images
Figure 2 for Evaluating Systemic Error Detection Methods using Synthetic Images
Figure 3 for Evaluating Systemic Error Detection Methods using Synthetic Images
Figure 4 for Evaluating Systemic Error Detection Methods using Synthetic Images
Viaarxiv icon

Use-Case-Grounded Simulations for Explanation Evaluation

Jun 05, 2022
Figure 1 for Use-Case-Grounded Simulations for Explanation Evaluation
Figure 2 for Use-Case-Grounded Simulations for Explanation Evaluation
Figure 3 for Use-Case-Grounded Simulations for Explanation Evaluation
Figure 4 for Use-Case-Grounded Simulations for Explanation Evaluation
Viaarxiv icon

Finding and Fixing Spurious Patterns with Explanations

Add code
Jun 03, 2021
Figure 1 for Finding and Fixing Spurious Patterns with Explanations
Figure 2 for Finding and Fixing Spurious Patterns with Explanations
Figure 3 for Finding and Fixing Spurious Patterns with Explanations
Figure 4 for Finding and Fixing Spurious Patterns with Explanations
Viaarxiv icon

Sanity Simulations for Saliency Methods

Add code
May 13, 2021
Figure 1 for Sanity Simulations for Saliency Methods
Figure 2 for Sanity Simulations for Saliency Methods
Figure 3 for Sanity Simulations for Saliency Methods
Figure 4 for Sanity Simulations for Saliency Methods
Viaarxiv icon

Towards Connecting Use Cases and Methods in Interpretable Machine Learning

Mar 10, 2021
Figure 1 for Towards Connecting Use Cases and Methods in Interpretable Machine Learning
Figure 2 for Towards Connecting Use Cases and Methods in Interpretable Machine Learning
Figure 3 for Towards Connecting Use Cases and Methods in Interpretable Machine Learning
Figure 4 for Towards Connecting Use Cases and Methods in Interpretable Machine Learning
Viaarxiv icon

A Learning Theoretic Perspective on Local Explainability

Nov 02, 2020
Figure 1 for A Learning Theoretic Perspective on Local Explainability
Figure 2 for A Learning Theoretic Perspective on Local Explainability
Viaarxiv icon

Explaining Groups of Points in Low-Dimensional Representations

Add code
Mar 18, 2020
Figure 1 for Explaining Groups of Points in Low-Dimensional Representations
Figure 2 for Explaining Groups of Points in Low-Dimensional Representations
Figure 3 for Explaining Groups of Points in Low-Dimensional Representations
Figure 4 for Explaining Groups of Points in Low-Dimensional Representations
Viaarxiv icon

Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)

Add code
May 31, 2019
Figure 1 for Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)
Figure 2 for Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)
Figure 3 for Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)
Figure 4 for Regularizing Black-box Models for Improved Interpretability (HILL 2019 Version)
Viaarxiv icon

Regularizing Black-box Models for Improved Interpretability

Add code
Feb 18, 2019
Figure 1 for Regularizing Black-box Models for Improved Interpretability
Figure 2 for Regularizing Black-box Models for Improved Interpretability
Figure 3 for Regularizing Black-box Models for Improved Interpretability
Figure 4 for Regularizing Black-box Models for Improved Interpretability
Viaarxiv icon